Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sdsrss/claude-mem-lite/plugin install claude-mem-liteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/sdsrss/claude-mem-lite/verify)<a href="https://agentmods.dev/commands/sdsrss/claude-mem-lite/verify"><img src="https://agentmods.dev/badge/commands/sdsrss/claude-mem-lite/verify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/sdsrss/claude-mem-lite/verify"><img src="https://agentmods.dev/badge/commands/sdsrss/claude-mem-lite/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.02220 |
| Opus 5.5 | $0.00030 | $0.00888 |
| Sonnet 5.5 | $0.00015 | $0.00444 |
| Haiku 4.5 | $0.00007 | $0.00222 |
Grade A, and why
verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/claude-mem-lite:verify — check memories against the code, then correct the stale ones
Memories go stale: a bug recorded as open gets fixed, a measurement gets retracted, a
mechanism is replaced. Measured on 118 live memories across 7 repos, ~10% were STALE and
~14% PARTIAL, and most went stale within a day of being saved. No automatic pass catches
this — cheap single-shot models misjudged it (precision 0.36) and model-written corrections
were false in 28 of 72 cases. What works is YOU reading the code: you propose, the user
approves the exact plan, and verify-apply is the only thing that writes.
Arguments
--from <YYYY-MM-DD>: only memories saved on or after this date (default: all live).--ids 12,34: only these memories.--project <name>: a project other than the current one.
Step 1 — Select
Get the exact project name first. For the current project (the usual case), run from the project's directory:
node "${CLAUDE_PLUGIN_ROOT}/cli.mjs" verify-apply --print-project
It prints the canonical name (e.g. dev--my-app) that verify-apply itself will target. For
another project, use the name the user gave only if it already has the parent--name shape;
otherwise ask. Always pass that exact name — export --project matches loosely and can pick a
neighbouring project from a short name.
node "${CLAUDE_PLUGIN_ROOT}/cli.mjs" export --project=<project> [--from <date>] > <scratch>/memories.json
Every row carries id, project, type, title, narrative, facts, lesson_learned,
files_modified, created_at. Check that every row's project is the name you passed. With
--ids, filter the file to those ids. The repository to check them against is the current
directory for the current project; for another project, ask the user where it lives.
files_modified holds both absolute and repo-relative paths. Tell the user how many memories
you are about to check.
Step 2 — Verify (read-only)
For EACH memory, answer: if this memory were shown to an agent working in this repo today, would anything it asserts mislead that agent?
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed bc6cc4a1dbb9
- 2d ago Changed · -2 lines · +6 tokens per session d95b2e3d8090
- 27d ago First seen · 157 lines · 68 tokens per session scan A cdd250050267
verify is a command published in the GitHub repository sdsrss/claude-mem-lite (67 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 2,220 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
Other commands, from other repositories
session-save
Save the current session state — decisions, modified files, current status, and next steps — to a handoff file for later resume.
drift-detect
Configuration drift detection command. Finds inconsistencies, orphaned components, and stale content in the Badi system.
wrap-up
End-of-day ritual command. Prepares the day for closure and sets the stage for tomorrow.
clear
Context-clearing command. Provides a seamless transition across session boundaries. Target: under 30 seconds.
sync
Mid-session context refresh command. Keeps context fresh and consistent during work.
memory-diff
Memory and knowledge-base limit check + global project comparison.